system

Abstract

The system according to this embodiment aims to perform appropriate content filtering according to the child's developmental level. [Solution] The system according to the embodiment comprises a determination unit, an adjustment unit, a message filtering unit, a content filtering unit, and an advertisement filtering unit. The determination unit determines the child's developmental level. The adjustment unit adjusts the filtering level based on the developmental level determined by the determination unit. The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. The content filtering unit deletes inappropriate content based on the filtering level adjusted by the adjustment unit. The advertisement filtering unit deletes inappropriate advertisements based on the filtering level adjusted by the adjustment unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, appropriate content filtering according to the development level of children has not been sufficiently performed, and there is room for improvement.

[0005] The system according to the embodiment aims to perform appropriate content filtering according to the development level of children.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a determination unit, an adjustment unit, a message filtering unit, a content filtering unit, and an advertising filtering unit. The determination unit determines the child's developmental level. The adjustment unit adjusts the filtering level based on the developmental level determined by the determination unit. The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. The content filtering unit deletes inappropriate content based on the filtering level adjusted by the adjustment unit. The advertising filtering unit deletes inappropriate advertisements based on the filtering level adjusted by the adjustment unit. [Effects of the Invention]

[0007] The system according to this embodiment can perform appropriate content filtering according to the child's developmental level. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The filtering system according to an embodiment of the present invention is a system that filters all content on a messaging application according to the child's developmental level. The filtering system uses a generating AI to adjust the filtering level according to the child's development. This provides an environment in which children can use messaging applications safely. For example, the filtering system targets all content on a messaging application and removes inappropriate messages, inappropriate content, and inappropriate advertisements according to the child's developmental level. The generating AI adjusts the filtering level based on the child's developmental level and displays only appropriate content. For example, when a child under 12 years old uses a messaging application, the generating AI removes inappropriate messages based on the child's developmental level. Inappropriate content and advertisements are also removed in the same way. This provides an environment in which children can use messaging applications with peace of mind. Furthermore, the generating AI dynamically adjusts the filtering level according to the child's development. For example, as the child grows, the filtering level is also adjusted as appropriate. This provides appropriate content according to the child's development. This system not only allows children to use messaging applications safely, but also allows advertisers to run advertisements that are appropriate for children. For example, educational advertisements and advertisements for children's products are displayed appropriately. In this way, a filtering system using generative AI provides an environment where children can use messaging applications with peace of mind, while also enabling advertisers to place appropriate advertisements. This allows the filtering system to provide content appropriate to the child's developmental level, creating a safe usage environment.

[0029] The filtering system according to the embodiment comprises a determination unit, an adjustment unit, a message filtering unit, a content filtering unit, and an advertising filtering unit. The determination unit determines the child's developmental level. The determination unit can determine the developmental level based, for example, the child's age, usage history, and parent settings. The determination unit can determine the developmental level based, for example, the child's age. The determination unit can also determine the developmental level based on usage history. Furthermore, the determination unit can also determine the developmental level based on parent settings. The adjustment unit adjusts the filtering level based on the developmental level determined by the determination unit. The adjustment unit can dynamically adjust the filtering level using, for example, a generative AI. The adjustment unit adjusts the filtering level in real time according to the child's developmental level. Furthermore, the adjustment unit can periodically re-evaluate and adjust the filtering level. The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. The message filtering unit can delete, for example, messages containing inappropriate words. Furthermore, the message filtering unit can delete messages containing inappropriate images. Furthermore, the message filtering unit can delete messages containing inappropriate links. The content filtering unit removes inappropriate content based on the filtering level adjusted by the adjustment unit. For example, the content filtering unit can remove content containing violent images. It can also remove content containing adult content. Furthermore, the content filtering unit can remove content containing discriminatory language. The advertising filtering unit removes inappropriate advertisements based on the filtering level adjusted by the adjustment unit. For example, the advertising filtering unit can remove fraudulent advertisements. It can also remove adult advertisements. Furthermore, the advertising filtering unit can remove advertisements containing violent content.As a result, the filtering system according to the embodiment can filter messages, content, and advertisements according to the child's developmental level, providing a safe environment.

[0030] The assessment unit determines the child's developmental level. For example, the assessment unit can determine the developmental level based on the child's age, usage history, and parental settings. Specifically, when determining the developmental level based on the child's age, it refers to a database of general developmental stages for each age group and considers the characteristics and behavioral patterns of the relevant age group. When determining the developmental level based on usage history, it collects data such as what content the child has viewed in the past, what applications they have used, and how much time they have spent on them, and analyzes this data. For example, it evaluates the frequency of use and learning outcomes of educational apps to understand the child's level of comprehension and range of interests. When determining the developmental level based on parental settings, it considers the filtering levels and restrictions set by the parents and sets standards to ensure the child's safety. This allows the assessment unit to comprehensively evaluate multiple factors and accurately determine the child's developmental level. Furthermore, the assessment unit can use AI to analyze this data and perform more advanced assessments. For example, it can use machine learning algorithms to model the child's behavioral patterns and learning outcomes and predict future developmental levels. This allows the assessment unit to provide filtering levels tailored to the child's individual needs and provide a safe and appropriate environment.

[0031] The adjustment unit adjusts the filtering level based on the developmental level determined by the judgment unit. The adjustment unit can dynamically adjust the filtering level using, for example, a generative AI. Specifically, the generative AI generates appropriate filtering criteria according to the child's developmental level and adjusts the filtering level in real time. For example, when the child is young, stricter filtering criteria are applied to eliminate inappropriate content and messages. On the other hand, as the child gets older, the filtering criteria are relaxed to respect the child's autonomy and judgment. The adjustment unit can also periodically re-evaluate and adjust the filtering level. For example, it can periodically evaluate the child's usage history and learning outcomes and review the filtering level. This allows the adjustment unit to respond flexibly to the child's growth and changes, and always provide the optimal filtering level. Furthermore, the adjustment unit can also customize the filtering level by considering parental settings and feedback. For example, if a parent sets settings to allow or prohibit specific content or messages, the adjustment unit adjusts the filtering level to reflect those settings. This allows the adjustment unit to provide an optimal filtering environment to ensure the child's safety while respecting the parent's wishes.

[0032] The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. For example, the message filtering unit can delete messages containing inappropriate words. Specifically, it analyzes the content of messages using natural language processing technology to detect inappropriate words and phrases. The message filtering unit can also delete messages containing inappropriate images. It analyzes images contained in messages using image recognition technology to detect violent or adult content. Furthermore, the message filtering unit can delete messages containing inappropriate links. It analyzes the content of the linked page and deletes the link if it contains inappropriate content. In this way, the message filtering unit can prevent children from encountering inappropriate messages and provide a safe communication environment. In addition, the message filtering unit can improve its filtering accuracy using AI. For example, it can use machine learning algorithms to learn patterns of inappropriate messages and quickly detect new inappropriate messages. In this way, the message filtering unit can always respond to the latest threats and ensure the safety of children.

[0033] The content filtering unit removes inappropriate content based on the filtering level adjusted by the adjustment unit. For example, the content filtering unit can remove content containing violent images. Specifically, it uses video analysis technology to analyze the images within the content and detect violent scenes or actions. The content filtering unit can also remove content containing adult content. It uses text analysis technology to analyze the text within the content and detect adult expressions or content. Furthermore, the content filtering unit can remove content containing discriminatory expressions. It uses natural language processing technology to analyze the text within the content and detect discriminatory expressions or content. This allows the content filtering unit to prevent children from encountering inappropriate content and provide a safe browsing environment. In addition, the content filtering unit can improve filtering accuracy using AI. For example, it can use machine learning algorithms to learn patterns of inappropriate content and quickly detect new inappropriate content. This allows the content filtering unit to constantly respond to the latest threats and ensure the safety of children.

[0034] The ad filtering unit removes inappropriate advertisements based on the filtering level adjusted by the adjustment unit. For example, the ad filtering unit can remove fraudulent advertisements. Specifically, it analyzes the content of advertisements and detects fraudulent elements and misleading expressions. The ad filtering unit can also remove adult advertisements. It analyzes the text and images of advertisements and removes them if they contain adult content. Furthermore, the ad filtering unit can remove advertisements containing violent content. It analyzes the video and text of advertisements and detects violent scenes and expressions. In this way, the ad filtering unit can prevent children from being exposed to inappropriate advertisements and provide a safe advertising environment. In addition, the ad filtering unit can improve its filtering accuracy using AI. For example, it can use machine learning algorithms to learn patterns of inappropriate advertisements and quickly detect new inappropriate advertisements. In this way, the ad filtering unit can always respond to the latest threats and ensure the safety of children.

[0035] The assessment unit can determine the developmental level based on the child's age, usage history, and parental settings. For example, the assessment unit can determine the developmental level based on the child's age. For example, the assessment unit can use an AI model that takes the child's age as input and outputs a developmental level to determine the developmental level. The assessment unit can also determine the developmental level based on usage history. For example, the assessment unit can use an AI model that takes the child's usage history as input and outputs a developmental level to determine the developmental level. Furthermore, the assessment unit can also determine the developmental level based on parental settings. For example, the assessment unit can use an AI model that takes parental settings as input and outputs a developmental level to determine the developmental level. This allows for accurate determination of the developmental level, taking into account the child's age, usage history, and parental settings.

[0036] The adjustment unit can dynamically adjust the filtering level based on the developmental level determined by the judgment unit. For example, the adjustment unit can dynamically adjust the filtering level using a generative AI. For instance, the adjustment unit can adjust the filtering level using a generative AI model that takes the developmental level as input and outputs a filtering level. The adjustment unit can also adjust the filtering level in real time. For example, the adjustment unit can adjust the filtering level in real time in response to changes in the developmental level. Furthermore, the adjustment unit can periodically re-evaluate and adjust the filtering level. For example, the adjustment unit can re-evaluate the developmental level at regular intervals and adjust the filtering level. This allows for the provision of appropriate content by dynamically adjusting the filtering level according to the developmental level.

[0037] The assessment unit can analyze a child's learning history and reflect it in the assessment of their developmental level. For example, the assessment unit can analyze data from a child's online learning platform and reflect the learning progress in the assessment of their developmental level. For example, the assessment unit can analyze learning progress using an AI model that takes online learning platform data as input and outputs learning progress. The assessment unit can also acquire a child's school performance data and use it to assess their developmental level. For example, the assessment unit can determine the developmental level using an AI model that takes school performance data as input and outputs developmental level. Furthermore, the assessment unit can analyze a child's home learning records and reflect them in the assessment of their developmental level. For example, the assessment unit can determine the developmental level using an AI model that takes home learning records as input and outputs developmental level. In this way, by analyzing the learning history, the assessment can be reflected in the assessment of the child's developmental level.

[0038] The assessment unit can analyze a child's daily behavioral patterns and use this information to determine their developmental level. For example, the assessment unit can analyze exercise data obtained from a child's smartwatch and use it to determine their developmental level. For instance, the assessment unit can use an AI model that takes smartwatch exercise data as input and outputs a developmental level to analyze the data. The assessment unit can also analyze daily behavioral data obtained from a child's smart home device and incorporate this into the developmental level determination. For example, the assessment unit can use an AI model that takes smart home device behavioral data as input and outputs a developmental level to analyze the data. Furthermore, the assessment unit can analyze a child's meal records and use their nutritional status to determine their developmental level. For example, the assessment unit can use an AI model that takes meal records as input and outputs a developmental level to analyze their nutritional status. In this way, by analyzing daily behavioral patterns, the assessment unit can use this information to determine the child's developmental level.

[0039] The assessment unit can monitor a child's health status and reflect this in determining their developmental level. For example, the assessment unit can analyze heart rate data obtained from a child's smartwatch and use it to determine their developmental level. For instance, the assessment unit can use an AI model that takes smartwatch heart rate data as input and outputs a developmental level to analyze the data. The assessment unit can also analyze sleep data obtained from a child's smart home device and reflect this in determining their developmental level. For example, the assessment unit can use an AI model that takes smart home device sleep data as input and analyze the data to output a developmental level. Furthermore, the assessment unit can obtain data from a child's regular health checkups and use it to determine their developmental level. For example, the assessment unit can use health checkup data as input and analyze the health checkup data to output a developmental level to analyze the data. In this way, monitoring the child's health status can be reflected in determining their developmental level.

[0040] The assessment unit can analyze a child's social media activity and use the analysis to determine their developmental level. For example, the assessment unit can analyze the content of a child's social media posts and reflect the results in determining their developmental level. For instance, the assessment unit can use an AI model that takes social media posts as input and outputs a developmental level to analyze the content. The assessment unit can also analyze a child's social media friendships and use the analysis to determine their developmental level. For example, the assessment unit can use an AI model that takes friendship data as input and outputs a developmental level to analyze the friendships. Furthermore, the assessment unit can analyze the frequency of a child's social media activity and reflect the results in determining their developmental level. For example, the assessment unit can use an AI model that takes activity frequency data as input and outputs a developmental level to analyze the activity frequency. In this way, social media activity can be analyzed and used to determine a child's developmental level.

[0041] The adjustment unit can dynamically adjust the filtering level according to the child's learning progress. For example, the adjustment unit can dynamically adjust the filtering level using generative AI. For example, the adjustment unit can adjust the filtering level using a generative AI model that takes learning progress as input and outputs a filtering level. For example, the adjustment unit can analyze data from an online learning platform and adjust the filtering level according to the learning progress. For example, the adjustment unit can analyze learning progress using a generative AI model that takes data from an online learning platform as input and outputs learning progress. The adjustment unit can also acquire the child's school grade data and adjust the filtering level according to the learning progress. For example, the adjustment unit can analyze the grade data using a generative AI model that takes school grade data as input and outputs a filtering level. Furthermore, the adjustment unit can analyze the child's homework records and adjust the filtering level according to the learning progress. For example, the adjustment unit can analyze homework records using a generative AI model that takes homework records as input and outputs a filtering level. By dynamically adjusting the filtering level according to the learning progress, appropriate content can be provided.

[0042] The adjustment unit can adjust the filtering level based on the child's usage time. The adjustment unit can adjust the filtering level using, for example, a generative AI. For example, the adjustment unit can adjust the filtering level using a generative AI model that takes usage time as input and outputs a filtering level. For example, the adjustment unit can analyze the usage time of a messaging application and tighten the filtering level if it is used for a long time. Conversely, the adjustment unit can also relax the filtering level if it is used for a short time. Furthermore, the adjustment unit can also adjust the filtering level based on an appropriate usage time. For example, the adjustment unit can analyze usage time using a generative AI model that takes usage time data as input and outputs a filtering level. This allows for appropriate filtering by adjusting the filtering level based on usage time.

[0043] The adjustment unit can adjust the filtering level based on the child's geographical location information. The adjustment unit can adjust the filtering level using, for example, generative AI. For example, the adjustment unit can adjust the filtering level using a generative AI model that takes geographical location information as input and outputs a filtering level. For example, the adjustment unit can tighten the filtering level if the child's current location is a school. It can also loosen the filtering level if the child's current location is home. Furthermore, the adjustment unit can appropriately adjust the filtering level if the child's current location is a public place. For example, the adjustment unit can analyze geographical location information using a generative AI model that takes geographical location data as input and outputs a filtering level. This allows for appropriate filtering by adjusting the filtering level based on geographical location information.

[0044] The adjustment unit can analyze a child's friendships and adjust the filtering level. For example, the adjustment unit can adjust the filtering level using generative AI. For instance, the adjustment unit can analyze friendships using a generative AI model that takes friendship data as input and outputs a filtering level. For example, the adjustment unit can analyze a child's social media friendships and relax the filtering level for interactions with trusted friends. It can also tighten the filtering level for interactions with unknown individuals. Furthermore, the adjustment unit can moderately adjust the filtering level for interactions with close friends. This allows for appropriate filtering by analyzing friendships.

[0045] The message filtering unit can analyze the content of messages and perform filtering according to the user's developmental level. For example, the message filtering unit can use AI to analyze the message content. For instance, it can use an AI model that takes the text data of a message as input and outputs inappropriate messages to analyze the message content. The message filtering unit can, for example, delete messages containing inappropriate words according to the user's developmental level. It can also delete messages containing inappropriate images according to the user's developmental level. Furthermore, it can delete messages containing inappropriate links according to the user's developmental level. This allows for filtering according to the user's developmental level by analyzing the content of messages.

[0046] The message filtering unit can perform filtering while considering the attribute information of the message sender. For example, the message filtering unit can analyze the sender's attribute information using AI. For instance, the message filtering unit can analyze the sender's attribute information using an AI model that takes the sender's attribute information as input and outputs a filtering level. For example, the message filtering unit can relax the filtering level if the sender is a trusted party. Conversely, the message filtering unit can tighten the filtering level if the sender is unknown. Furthermore, the message filtering unit can appropriately adjust the filtering level if the sender is a close friend. In this way, appropriate message filtering becomes possible by considering the sender's attribute information.

[0047] The message filtering unit can perform filtering based on the message transmission time. For example, the message filtering unit can analyze transmission time using AI. For instance, the message filtering unit can analyze transmission time using an AI model that takes transmission time data as input and outputs a filtering level. For example, the message filtering unit can apply a stricter filtering level to messages sent late at night. Conversely, it can also relax the filtering level for messages sent during the day. Furthermore, it can apply a moderate filtering level to messages sent in the evening. This allows for appropriate message filtering by performing filtering based on transmission time.

[0048] The message filtering unit can improve the accuracy of filtering based on the relevance of messages. For example, the message filtering unit can analyze the relevance of messages using AI. For instance, the message filtering unit can analyze the relevance of messages using an AI model that takes message content as input and outputs relevance. For example, the message filtering unit can relax the filtering level when the message content is highly relevant. Conversely, the message filtering unit can tighten the filtering level when the message content is less relevant. Furthermore, the message filtering unit can apply an appropriate filtering level when the message content has a moderate level of relevance. This improves the accuracy of filtering based on the relevance of messages, enabling appropriate message filtering.

[0049] The content filtering unit can filter content according to its category. For example, the content filtering unit can analyze content categories using AI. For instance, it can analyze content categories using an AI model that takes content metadata as input and outputs categories. The content filtering unit can, for example, relax the filtering level for educational content. It can also apply a moderate filtering level to entertainment content. Furthermore, it can apply a strict filtering level to violent content. This allows for appropriate content filtering by filtering content according to its category.

[0050] The content filtering unit can analyze content browsing history and improve the accuracy of filtering. For example, the content filtering unit can analyze browsing history using AI. For instance, the content filtering unit can analyze browsing history using an AI model that takes browsing history data as input and outputs a filtering level. For example, the content filtering unit can analyze a child's past browsing history and prioritize displaying highly relevant content. Furthermore, the content filtering unit can analyze past browsing history and delete inappropriate content. In addition, the content filtering unit can analyze past browsing history to improve the accuracy of filtering. Thus, by analyzing browsing history, the accuracy of filtering can be improved.

[0051] The content filtering unit can perform filtering while considering the attribute information of the content creator. For example, the content filtering unit can analyze the creator's attribute information using AI. For example, the content filtering unit can analyze the creator's attribute information using an AI model that takes the creator's attribute information as input and outputs a filtering level. For example, the content filtering unit can relax the filtering level if the creator is a trusted person. Conversely, the content filtering unit can tighten the filtering level if the creator is an unknown person. Furthermore, the content filtering unit can appropriately adjust the filtering level if the creator is a close friend. In this way, appropriate content filtering becomes possible by considering the creator's attribute information.

[0052] The content filtering unit can improve the accuracy of filtering based on the relevance of the content. For example, the content filtering unit can analyze the relevance of content using AI. For example, the content filtering unit can analyze the relevance of content using an AI model that takes the content as input and outputs the relevance. For example, the content filtering unit can relax the filtering level when the content is highly relevant. Conversely, the content filtering unit can tighten the filtering level when the content is not highly relevant. Furthermore, the content filtering unit can apply an appropriate filtering level when the content is moderately relevant. This improves the accuracy of filtering based on the relevance of the content, enabling appropriate content filtering.

[0053] The ad filtering unit can filter ads according to their category. For example, the ad filtering unit can analyze ad categories using AI. For instance, it can analyze ad categories using an AI model that takes ad metadata as input and outputs categories. For example, the ad filtering unit can relax the filtering level for educational ads. It can also apply a moderate filtering level to entertainment ads. Furthermore, it can apply a strict filtering level to violent ads. This allows for appropriate ad filtering by filtering according to the ad category.

[0054] The ad filtering unit can analyze ad display history and improve the accuracy of filtering. For example, the ad filtering unit can analyze display history using AI. For instance, the ad filtering unit can analyze display history using an AI model that takes display history data as input and outputs a filtering level. For example, the ad filtering unit can analyze a child's past ad display history and prioritize displaying highly relevant ads. Furthermore, the ad filtering unit can analyze past ad display history and remove inappropriate ads. In addition, the ad filtering unit can analyze past ad display history to improve the accuracy of filtering. This means that by analyzing display history, the accuracy of filtering can be improved.

[0055] The ad filtering unit can perform filtering based on the display time of the ads. For example, the ad filtering unit can analyze the display time using AI. For instance, the ad filtering unit can analyze the display time using an AI model that takes display time data as input and outputs a filtering level. For example, the ad filtering unit can apply a stricter filtering level to ads displayed late at night. Conversely, the ad filtering unit can also relax the filtering level for ads displayed during the day. Furthermore, the ad filtering unit can apply a moderate filtering level to ads displayed in the evening. This enables appropriate ad filtering by performing filtering based on the display time.

[0056] The ad filtering unit can improve the accuracy of filtering based on the relevance of the ads. For example, the ad filtering unit can analyze the relevance of ads using AI. For instance, the ad filtering unit can analyze the relevance of ads using an AI model that takes the ad content as input and outputs relevance. For example, the ad filtering unit can relax the filtering level if the ad content is highly relevant. Conversely, the ad filtering unit can tighten the filtering level if the ad content is not relevant. Furthermore, the ad filtering unit can apply an appropriate filtering level if the ad content has a moderate level of relevance. This improves the accuracy of filtering based on the relevance of the ads, enabling appropriate ad filtering.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The filtering system may also include a learning progress monitoring unit that monitors the child's learning progress. The learning progress monitoring unit analyzes data from the child's online learning platform and evaluates their learning progress. For example, the learning progress monitoring unit can analyze learning progress using an AI model that takes data from the online learning platform as input and outputs learning progress. The learning progress monitoring unit can also acquire the child's school grade data and evaluate their learning progress. Furthermore, the learning progress monitoring unit can analyze records of the child's homework and evaluate their learning progress. As a result, by using the learning progress monitoring unit, the filtering level can be adjusted based on the child's learning progress.

[0059] The filtering system can also include a health monitoring unit to monitor the child's health status. The health monitoring unit analyzes heart rate data acquired from the child's smartwatch and evaluates their health status. For example, the health monitoring unit can analyze heart rate data using an AI model that takes smartwatch heart rate data as input and outputs health status. The health monitoring unit can also analyze sleep data acquired from the child's smart home device and evaluate their health status. Furthermore, the health monitoring unit can acquire data from the child's regular health checkups and evaluate their health status. This allows the filtering level to be adjusted based on the child's health status by using the health monitoring unit.

[0060] The filtering system can also include a behavioral analysis unit that analyzes the child's daily behavioral patterns. The behavioral analysis unit analyzes exercise data acquired from the child's smartwatch and evaluates the behavioral patterns. For example, the behavioral analysis unit can analyze the exercise data using an AI model that takes smartwatch exercise data as input and outputs behavioral patterns. The behavioral analysis unit can also analyze daily behavioral data acquired from the child's smart home devices and evaluate the behavioral patterns. Furthermore, the behavioral analysis unit can analyze the child's meal records and evaluate their nutritional status. As a result, by using the behavioral analysis unit, the filtering level can be adjusted based on the child's daily behavioral patterns.

[0061] The filtering system may also include a social media analysis unit that analyzes children's social media activity. The social media analysis unit analyzes the content of children's social media posts and reflects this in the determination of their developmental level. For example, the social media analysis unit can analyze social media posts using an AI model that takes social media posts as input and outputs a developmental level. The social media analysis unit can also analyze children's social media friendships and use this to determine their developmental level. Furthermore, the social media analysis unit can analyze the frequency of children's social media activity and reflect this in the determination of their developmental level. As a result, by using the social media analysis unit, the filtering level can be adjusted based on children's social media activity.

[0062] The filtering system may further include a location information analysis unit that analyzes the child's geographical location. The location information analysis unit analyzes the child's current location and adjusts the filtering level. For example, the location information analysis unit can analyze geographical location information using an AI model that takes geographical location information as input and outputs a filtering level. For example, the location information analysis unit can tighten the filtering level if the child's current location is at school. It can also loosen the filtering level if the child's current location is at home. Furthermore, the location information analysis unit can appropriately adjust the filtering level if the child's current location is in a public place. In this way, by using the location information analysis unit, the filtering level can be adjusted based on the child's geographical location.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The assessment unit determines the child's developmental level. The assessment unit can determine the developmental level based, for example, the child's age, usage history, and parental settings. Step 2: The adjustment unit adjusts the filtering level based on the developmental level determined by the judgment unit. The adjustment unit can dynamically adjust the filtering level using, for example, a generative AI. The adjustment unit can also periodically re-evaluate and adjust the filtering level. Step 3: The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. The message filtering unit can delete messages containing inappropriate words, inappropriate images, or inappropriate links, for example. Step 4: The content filtering unit removes inappropriate content based on the filtering level adjusted by the adjustment unit. The content filtering unit can remove content such as violent images, adult content, and discriminatory language. Step 5: The ad filtering unit removes inappropriate ads based on the filtering level adjusted by the adjustment unit. The ad filtering unit can remove, for example, fraudulent ads, adult ads, and ads containing violent content.

[0065] (Example of form 2) The filtering system according to an embodiment of the present invention is a system that filters all content on a messaging application according to the child's developmental level. The filtering system uses a generating AI to adjust the filtering level according to the child's development. This provides an environment in which children can use messaging applications safely. For example, the filtering system targets all content on a messaging application and removes inappropriate messages, inappropriate content, and inappropriate advertisements according to the child's developmental level. The generating AI adjusts the filtering level based on the child's developmental level and displays only appropriate content. For example, when a child under 12 years old uses a messaging application, the generating AI removes inappropriate messages based on the child's developmental level. Inappropriate content and advertisements are also removed in the same way. This provides an environment in which children can use messaging applications with peace of mind. Furthermore, the generating AI dynamically adjusts the filtering level according to the child's development. For example, as the child grows, the filtering level is also adjusted as appropriate. This provides appropriate content according to the child's development. This system not only allows children to use messaging applications safely, but also allows advertisers to run advertisements that are appropriate for children. For example, educational advertisements and advertisements for children's products are displayed appropriately. In this way, a filtering system using generative AI provides an environment where children can use messaging applications with peace of mind, while also enabling advertisers to place appropriate advertisements. This allows the filtering system to provide content appropriate to the child's developmental level, creating a safe usage environment.

[0066] The filtering system according to the embodiment comprises a determination unit, an adjustment unit, a message filtering unit, a content filtering unit, and an advertising filtering unit. The determination unit determines the child's developmental level. The determination unit can determine the developmental level based, for example, the child's age, usage history, and parent settings. The determination unit can determine the developmental level based, for example, the child's age. The determination unit can also determine the developmental level based on usage history. Furthermore, the determination unit can also determine the developmental level based on parent settings. The adjustment unit adjusts the filtering level based on the developmental level determined by the determination unit. The adjustment unit can dynamically adjust the filtering level using, for example, a generative AI. The adjustment unit adjusts the filtering level in real time according to the child's developmental level. Furthermore, the adjustment unit can periodically re-evaluate and adjust the filtering level. The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. The message filtering unit can delete, for example, messages containing inappropriate words. Furthermore, the message filtering unit can delete messages containing inappropriate images. Furthermore, the message filtering unit can delete messages containing inappropriate links. The content filtering unit removes inappropriate content based on the filtering level adjusted by the adjustment unit. For example, the content filtering unit can remove content containing violent images. It can also remove content containing adult content. Furthermore, the content filtering unit can remove content containing discriminatory language. The advertising filtering unit removes inappropriate advertisements based on the filtering level adjusted by the adjustment unit. For example, the advertising filtering unit can remove fraudulent advertisements. It can also remove adult advertisements. Furthermore, the advertising filtering unit can remove advertisements containing violent content.As a result, the filtering system according to the embodiment can filter messages, content, and advertisements according to the child's developmental level, providing a safe environment.

[0067] The assessment unit determines the child's developmental level. For example, the assessment unit can determine the developmental level based on the child's age, usage history, and parental settings. Specifically, when determining the developmental level based on the child's age, it refers to a database of general developmental stages for each age group and considers the characteristics and behavioral patterns of the relevant age group. When determining the developmental level based on usage history, it collects data such as what content the child has viewed in the past, what applications they have used, and how much time they have spent on them, and analyzes this data. For example, it evaluates the frequency of use and learning outcomes of educational apps to understand the child's level of comprehension and range of interests. When determining the developmental level based on parental settings, it considers the filtering levels and restrictions set by the parents and sets standards to ensure the child's safety. This allows the assessment unit to comprehensively evaluate multiple factors and accurately determine the child's developmental level. Furthermore, the assessment unit can use AI to analyze this data and perform more advanced assessments. For example, it can use machine learning algorithms to model the child's behavioral patterns and learning outcomes and predict future developmental levels. This allows the assessment unit to provide filtering levels tailored to the child's individual needs and provide a safe and appropriate environment.

[0068] The adjustment unit adjusts the filtering level based on the developmental level determined by the judgment unit. The adjustment unit can dynamically adjust the filtering level using, for example, a generative AI. Specifically, the generative AI generates appropriate filtering criteria according to the child's developmental level and adjusts the filtering level in real time. For example, when the child is young, stricter filtering criteria are applied to eliminate inappropriate content and messages. On the other hand, as the child gets older, the filtering criteria are relaxed to respect the child's autonomy and judgment. The adjustment unit can also periodically re-evaluate and adjust the filtering level. For example, it can periodically evaluate the child's usage history and learning outcomes and review the filtering level. This allows the adjustment unit to respond flexibly to the child's growth and changes, and always provide the optimal filtering level. Furthermore, the adjustment unit can also customize the filtering level by considering parental settings and feedback. For example, if a parent sets settings to allow or prohibit specific content or messages, the adjustment unit adjusts the filtering level to reflect those settings. This allows the adjustment unit to provide an optimal filtering environment to ensure the child's safety while respecting the parent's wishes.

[0069] The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. For example, the message filtering unit can delete messages containing inappropriate words. Specifically, it analyzes the content of messages using natural language processing technology to detect inappropriate words and phrases. The message filtering unit can also delete messages containing inappropriate images. It analyzes images contained in messages using image recognition technology to detect violent or adult content. Furthermore, the message filtering unit can delete messages containing inappropriate links. It analyzes the content of the linked page and deletes the link if it contains inappropriate content. In this way, the message filtering unit can prevent children from encountering inappropriate messages and provide a safe communication environment. In addition, the message filtering unit can improve its filtering accuracy using AI. For example, it can use machine learning algorithms to learn patterns of inappropriate messages and quickly detect new inappropriate messages. In this way, the message filtering unit can always respond to the latest threats and ensure the safety of children.

[0070] The content filtering unit removes inappropriate content based on the filtering level adjusted by the adjustment unit. For example, the content filtering unit can remove content containing violent images. Specifically, it uses video analysis technology to analyze the images within the content and detect violent scenes or actions. The content filtering unit can also remove content containing adult content. It uses text analysis technology to analyze the text within the content and detect adult expressions or content. Furthermore, the content filtering unit can remove content containing discriminatory expressions. It uses natural language processing technology to analyze the text within the content and detect discriminatory expressions or content. This allows the content filtering unit to prevent children from encountering inappropriate content and provide a safe browsing environment. In addition, the content filtering unit can improve filtering accuracy using AI. For example, it can use machine learning algorithms to learn patterns of inappropriate content and quickly detect new inappropriate content. This allows the content filtering unit to constantly respond to the latest threats and ensure the safety of children.

[0071] The ad filtering unit removes inappropriate advertisements based on the filtering level adjusted by the adjustment unit. For example, the ad filtering unit can remove fraudulent advertisements. Specifically, it analyzes the content of advertisements and detects fraudulent elements and misleading expressions. The ad filtering unit can also remove adult advertisements. It analyzes the text and images of advertisements and removes them if they contain adult content. Furthermore, the ad filtering unit can remove advertisements containing violent content. It analyzes the video and text of advertisements and detects violent scenes and expressions. In this way, the ad filtering unit can prevent children from being exposed to inappropriate advertisements and provide a safe advertising environment. In addition, the ad filtering unit can improve its filtering accuracy using AI. For example, it can use machine learning algorithms to learn patterns of inappropriate advertisements and quickly detect new inappropriate advertisements. In this way, the ad filtering unit can always respond to the latest threats and ensure the safety of children.

[0072] The assessment unit can determine the developmental level based on the child's age, usage history, and parental settings. For example, the assessment unit can determine the developmental level based on the child's age. For example, the assessment unit can use an AI model that takes the child's age as input and outputs a developmental level to determine the developmental level. The assessment unit can also determine the developmental level based on usage history. For example, the assessment unit can use an AI model that takes the child's usage history as input and outputs a developmental level to determine the developmental level. Furthermore, the assessment unit can also determine the developmental level based on parental settings. For example, the assessment unit can use an AI model that takes parental settings as input and outputs a developmental level to determine the developmental level. This allows for accurate determination of the developmental level, taking into account the child's age, usage history, and parental settings.

[0073] The adjustment unit can dynamically adjust the filtering level based on the developmental level determined by the judgment unit. For example, the adjustment unit can dynamically adjust the filtering level using a generative AI. For instance, the adjustment unit can adjust the filtering level using a generative AI model that takes the developmental level as input and outputs a filtering level. The adjustment unit can also adjust the filtering level in real time. For example, the adjustment unit can adjust the filtering level in real time in response to changes in the developmental level. Furthermore, the adjustment unit can periodically re-evaluate and adjust the filtering level. For example, the adjustment unit can re-evaluate the developmental level at regular intervals and adjust the filtering level. This allows for the provision of appropriate content by dynamically adjusting the filtering level according to the developmental level.

[0074] The assessment unit can estimate a child's emotions and correct the developmental level assessment based on the estimated emotions. The assessment unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the assessment unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. Alternatively, the assessment unit can estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, the assessment unit can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The assessment unit corrects the developmental level assessment based on the estimated emotions of the child. For example, the assessment unit can correct the developmental level assessment based on an emotion score. The assessment unit can also re-evaluate specific emotional states and correct the developmental level assessment. This allows for a more accurate assessment of the developmental level by correcting the assessment based on the child's emotions.

[0075] The assessment unit can analyze a child's learning history and reflect it in the assessment of their developmental level. For example, the assessment unit can analyze data from a child's online learning platform and reflect the learning progress in the assessment of their developmental level. For example, the assessment unit can analyze learning progress using an AI model that takes online learning platform data as input and outputs learning progress. The assessment unit can also acquire a child's school performance data and use it to assess their developmental level. For example, the assessment unit can determine the developmental level using an AI model that takes school performance data as input and outputs developmental level. Furthermore, the assessment unit can analyze a child's home learning records and reflect them in the assessment of their developmental level. For example, the assessment unit can determine the developmental level using an AI model that takes home learning records as input and outputs developmental level. In this way, by analyzing the learning history, the assessment can be reflected in the assessment of the child's developmental level.

[0076] The assessment unit can analyze a child's daily behavioral patterns and use this information to determine their developmental level. For example, the assessment unit can analyze exercise data obtained from a child's smartwatch and use it to determine their developmental level. For instance, the assessment unit can use an AI model that takes smartwatch exercise data as input and outputs a developmental level to analyze the data. The assessment unit can also analyze daily behavioral data obtained from a child's smart home device and incorporate this into the developmental level determination. For example, the assessment unit can use an AI model that takes smart home device behavioral data as input and outputs a developmental level to analyze the data. Furthermore, the assessment unit can analyze a child's meal records and use their nutritional status to determine their developmental level. For example, the assessment unit can use an AI model that takes meal records as input and outputs a developmental level to analyze their nutritional status. In this way, by analyzing daily behavioral patterns, the assessment unit can use this information to determine the child's developmental level.

[0077] The judgment unit can estimate the child's emotions and adjust the display method of the judgment result based on the estimated emotions. The judgment unit estimates the child's emotions using an emotion estimation function, for example, using an emotion engine or generative AI. For example, the judgment unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. The judgment unit can also estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the judgment unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The judgment unit adjusts the display method of the judgment result based on the estimated emotions of the child. For example, the judgment unit can provide a simple display method if the emotions are unstable. The judgment unit can also provide a detailed display method if the emotions are stable. Furthermore, the judgment unit can provide a visually stimulating display method if the emotions are heightened. By adjusting the display method based on the child's emotions, it becomes possible to provide more appropriate information.

[0078] The assessment unit can monitor a child's health status and reflect this in determining their developmental level. For example, the assessment unit can analyze heart rate data obtained from a child's smartwatch and use it to determine their developmental level. For instance, the assessment unit can use an AI model that takes smartwatch heart rate data as input and outputs a developmental level to analyze the data. The assessment unit can also analyze sleep data obtained from a child's smart home device and reflect this in determining their developmental level. For example, the assessment unit can use an AI model that takes smart home device sleep data as input and analyze the data to output a developmental level. Furthermore, the assessment unit can obtain data from a child's regular health checkups and use it to determine their developmental level. For example, the assessment unit can use health checkup data as input and analyze the health checkup data to output a developmental level to analyze the data. In this way, monitoring the child's health status can be reflected in determining their developmental level.

[0079] The assessment unit can analyze a child's social media activity and use the analysis to determine their developmental level. For example, the assessment unit can analyze the content of a child's social media posts and reflect the results in determining their developmental level. For instance, the assessment unit can use an AI model that takes social media posts as input and outputs a developmental level to analyze the content. The assessment unit can also analyze a child's social media friendships and use the analysis to determine their developmental level. For example, the assessment unit can use an AI model that takes friendship data as input and outputs a developmental level to analyze the friendships. Furthermore, the assessment unit can analyze the frequency of a child's social media activity and reflect the results in determining their developmental level. For example, the assessment unit can use an AI model that takes activity frequency data as input and outputs a developmental level to analyze the activity frequency. In this way, social media activity can be analyzed and used to determine a child's developmental level.

[0080] The adjustment unit can estimate the child's emotions and fine-tune the filtering level based on the estimated emotions. The adjustment unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the adjustment unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. It can also estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the adjustment unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The adjustment unit fine-tunes the filtering level based on the estimated emotions of the child. For example, the adjustment unit can tighten the filtering level if the emotions are unstable. It can also relax the filtering level if the emotions are stable. Furthermore, it can adjust the filtering level appropriately if the emotions are heightened. This allows for more appropriate filtering by fine-tuning the filtering level based on the child's emotions.

[0081] The adjustment unit can dynamically adjust the filtering level according to the child's learning progress. For example, the adjustment unit can dynamically adjust the filtering level using generative AI. For example, the adjustment unit can adjust the filtering level using a generative AI model that takes learning progress as input and outputs a filtering level. For example, the adjustment unit can analyze data from an online learning platform and adjust the filtering level according to the learning progress. For example, the adjustment unit can analyze learning progress using a generative AI model that takes data from an online learning platform as input and outputs learning progress. The adjustment unit can also acquire the child's school grade data and adjust the filtering level according to the learning progress. For example, the adjustment unit can analyze the grade data using a generative AI model that takes school grade data as input and outputs a filtering level. Furthermore, the adjustment unit can analyze the child's homework records and adjust the filtering level according to the learning progress. For example, the adjustment unit can analyze homework records using a generative AI model that takes homework records as input and outputs a filtering level. By dynamically adjusting the filtering level according to the learning progress, appropriate content can be provided.

[0082] The adjustment unit can adjust the filtering level based on the child's usage time. The adjustment unit can adjust the filtering level using, for example, a generative AI. For example, the adjustment unit can adjust the filtering level using a generative AI model that takes usage time as input and outputs a filtering level. For example, the adjustment unit can analyze the usage time of a messaging application and tighten the filtering level if it is used for a long time. Conversely, the adjustment unit can also relax the filtering level if it is used for a short time. Furthermore, the adjustment unit can also adjust the filtering level based on an appropriate usage time. For example, the adjustment unit can analyze usage time using a generative AI model that takes usage time data as input and outputs a filtering level. This allows for appropriate filtering by adjusting the filtering level based on usage time.

[0083] The adjustment unit can estimate the child's emotions and determine the frequency of filtering level adjustments based on the estimated emotions. The adjustment unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the adjustment unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. The adjustment unit can also estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the adjustment unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The adjustment unit determines the frequency of filtering level adjustments based on the estimated emotions of the child. For example, the adjustment unit can adjust the filtering level frequently if the emotions are unstable. The adjustment unit can also reduce the frequency of filtering level adjustments if the emotions are stable. Furthermore, the adjustment unit can adjust the filtering level at an appropriate frequency if the emotions are heightened. This allows for appropriate filtering by determining the adjustment frequency based on the child's emotions.

[0084] The adjustment unit can adjust the filtering level based on the child's geographical location information. The adjustment unit can adjust the filtering level using, for example, generative AI. For example, the adjustment unit can adjust the filtering level using a generative AI model that takes geographical location information as input and outputs a filtering level. For example, the adjustment unit can tighten the filtering level if the child's current location is a school. It can also loosen the filtering level if the child's current location is home. Furthermore, the adjustment unit can appropriately adjust the filtering level if the child's current location is a public place. For example, the adjustment unit can analyze geographical location information using a generative AI model that takes geographical location data as input and outputs a filtering level. This allows for appropriate filtering by adjusting the filtering level based on geographical location information.

[0085] The adjustment unit can analyze a child's friendships and adjust the filtering level. For example, the adjustment unit can adjust the filtering level using generative AI. For instance, the adjustment unit can analyze friendships using a generative AI model that takes friendship data as input and outputs a filtering level. For example, the adjustment unit can analyze a child's social media friendships and relax the filtering level for interactions with trusted friends. It can also tighten the filtering level for interactions with unknown individuals. Furthermore, the adjustment unit can moderately adjust the filtering level for interactions with close friends. This allows for appropriate filtering by analyzing friendships.

[0086] The message filtering unit can estimate a child's emotions and adjust the criteria for deleting inappropriate messages based on the estimated emotions. The message filtering unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the message filtering unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. It can also estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, it can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The message filtering unit adjusts the criteria for deleting inappropriate messages based on the estimated emotions of the child. For example, the message filtering unit can apply strict deletion criteria when emotions are unstable. It can also apply lenient deletion criteria when emotions are stable. Furthermore, it can apply moderate deletion criteria when emotions are heightened. This allows for appropriate message filtering by adjusting the deletion criteria based on the child's emotions.

[0087] The message filtering unit can analyze the content of messages and perform filtering according to the user's developmental level. For example, the message filtering unit can use AI to analyze the message content. For instance, it can use an AI model that takes the text data of a message as input and outputs inappropriate messages to analyze the message content. The message filtering unit can, for example, delete messages containing inappropriate words according to the user's developmental level. It can also delete messages containing inappropriate images according to the user's developmental level. Furthermore, it can delete messages containing inappropriate links according to the user's developmental level. This allows for filtering according to the user's developmental level by analyzing the content of messages.

[0088] The message filtering unit can perform filtering while considering the attribute information of the message sender. For example, the message filtering unit can analyze the sender's attribute information using AI. For instance, the message filtering unit can analyze the sender's attribute information using an AI model that takes the sender's attribute information as input and outputs a filtering level. For example, the message filtering unit can relax the filtering level if the sender is a trusted party. Conversely, the message filtering unit can tighten the filtering level if the sender is unknown. Furthermore, the message filtering unit can appropriately adjust the filtering level if the sender is a close friend. In this way, appropriate message filtering becomes possible by considering the sender's attribute information.

[0089] The message filtering unit can estimate a child's emotions and determine the priority of messages to delete based on the estimated emotions. The message filtering unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the message filtering unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. Alternatively, the message filtering unit can estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, the message filtering unit can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The message filtering unit determines the priority of messages to delete based on the estimated emotions of the child. For example, if the child's emotions are unstable, the message filtering unit can prioritize the deletion of inappropriate messages. If the child's emotions are stable, the message filtering unit can also relax the deletion priority. Furthermore, if the child's emotions are heightened, the message filtering unit can delete messages with an appropriate priority. This allows for appropriate message filtering by determining the priority of messages to delete based on the child's emotions.

[0090] The message filtering unit can perform filtering based on the message transmission time. For example, the message filtering unit can analyze transmission time using AI. For instance, the message filtering unit can analyze transmission time using an AI model that takes transmission time data as input and outputs a filtering level. For example, the message filtering unit can apply a stricter filtering level to messages sent late at night. Conversely, it can also relax the filtering level for messages sent during the day. Furthermore, it can apply a moderate filtering level to messages sent in the evening. This allows for appropriate message filtering by performing filtering based on transmission time.

[0091] The message filtering unit can improve the accuracy of filtering based on the relevance of messages. For example, the message filtering unit can analyze the relevance of messages using AI. For instance, the message filtering unit can analyze the relevance of messages using an AI model that takes message content as input and outputs relevance. For example, the message filtering unit can relax the filtering level when the message content is highly relevant. Conversely, the message filtering unit can tighten the filtering level when the message content is less relevant. Furthermore, the message filtering unit can apply an appropriate filtering level when the message content has a moderate level of relevance. This improves the accuracy of filtering based on the relevance of messages, enabling appropriate message filtering.

[0092] The content filtering unit can estimate a child's emotions and adjust the criteria for deleting inappropriate content based on the estimated emotions. The content filtering unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the content filtering unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. It can also estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, the content filtering unit can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The content filtering unit adjusts the criteria for deleting inappropriate content based on the estimated emotions of the child. For example, the content filtering unit can apply strict deletion criteria if the emotions are unstable. It can also apply lenient deletion criteria if the emotions are stable. Furthermore, it can apply moderate deletion criteria if the emotions are heightened. This allows for appropriate content filtering by adjusting the deletion criteria based on the child's emotions.

[0093] The content filtering unit can filter content according to its category. For example, the content filtering unit can analyze content categories using AI. For instance, it can analyze content categories using an AI model that takes content metadata as input and outputs categories. The content filtering unit can, for example, relax the filtering level for educational content. It can also apply a moderate filtering level to entertainment content. Furthermore, it can apply a strict filtering level to violent content. This allows for appropriate content filtering by filtering content according to its category.

[0094] The content filtering unit can analyze content browsing history and improve the accuracy of filtering. For example, the content filtering unit can analyze browsing history using AI. For instance, the content filtering unit can analyze browsing history using an AI model that takes browsing history data as input and outputs a filtering level. For example, the content filtering unit can analyze a child's past browsing history and prioritize displaying highly relevant content. Furthermore, the content filtering unit can analyze past browsing history and delete inappropriate content. In addition, the content filtering unit can analyze past browsing history to improve the accuracy of filtering. Thus, by analyzing browsing history, the accuracy of filtering can be improved.

[0095] The content filtering unit can estimate a child's emotions and determine the priority of content to delete based on the estimated emotions. The content filtering unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the content filtering unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. It can also estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, it can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The content filtering unit determines the priority of content to delete based on the estimated emotions of the child. For example, if the child's emotions are unstable, the content filtering unit can prioritize the deletion of inappropriate content. It can also relax the deletion priority if the child's emotions are stable. Furthermore, it can delete content with an appropriate priority if the child's emotions are heightened. This allows for appropriate content filtering by determining the priority of content to delete based on the child's emotions.

[0096] The content filtering unit can perform filtering while considering the attribute information of the content creator. For example, the content filtering unit can analyze the creator's attribute information using AI. For example, the content filtering unit can analyze the creator's attribute information using an AI model that takes the creator's attribute information as input and outputs a filtering level. For example, the content filtering unit can relax the filtering level if the creator is a trusted person. Conversely, the content filtering unit can tighten the filtering level if the creator is an unknown person. Furthermore, the content filtering unit can appropriately adjust the filtering level if the creator is a close friend. In this way, appropriate content filtering becomes possible by considering the creator's attribute information.

[0097] The content filtering unit can improve the accuracy of filtering based on the relevance of the content. For example, the content filtering unit can analyze the relevance of content using AI. For example, the content filtering unit can analyze the relevance of content using an AI model that takes the content as input and outputs the relevance. For example, the content filtering unit can relax the filtering level when the content is highly relevant. Conversely, the content filtering unit can tighten the filtering level when the content is not highly relevant. Furthermore, the content filtering unit can apply an appropriate filtering level when the content is moderately relevant. This improves the accuracy of filtering based on the relevance of the content, enabling appropriate content filtering.

[0098] The ad filtering unit can estimate a child's emotions and adjust the criteria for removing inappropriate ads based on the estimated emotions. The ad filtering unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the ad filtering unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. It can also estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, the ad filtering unit can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The ad filtering unit adjusts the criteria for removing inappropriate ads based on the estimated emotions of the child. For example, the ad filtering unit can apply stricter removal criteria if the child's emotions are unstable. It can also apply more lenient removal criteria if the child's emotions are stable. Furthermore, it can apply moderate removal criteria if the child's emotions are heightened. This allows for appropriate ad filtering by adjusting the removal criteria based on the child's emotions.

[0099] The ad filtering unit can filter ads according to their category. For example, the ad filtering unit can analyze ad categories using AI. For instance, it can analyze ad categories using an AI model that takes ad metadata as input and outputs categories. For example, the ad filtering unit can relax the filtering level for educational ads. It can also apply a moderate filtering level to entertainment ads. Furthermore, it can apply a strict filtering level to violent ads. This allows for appropriate ad filtering by filtering according to the ad category.

[0100] The ad filtering unit can analyze ad display history and improve the accuracy of filtering. For example, the ad filtering unit can analyze display history using AI. For instance, the ad filtering unit can analyze display history using an AI model that takes display history data as input and outputs a filtering level. For example, the ad filtering unit can analyze a child's past ad display history and prioritize displaying highly relevant ads. Furthermore, the ad filtering unit can analyze past ad display history and remove inappropriate ads. In addition, the ad filtering unit can analyze past ad display history to improve the accuracy of filtering. This means that by analyzing display history, the accuracy of filtering can be improved.

[0101] The ad filtering unit can estimate a child's emotions and determine the priority of ads to remove based on the estimated emotions. The ad filtering unit estimates a child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the ad filtering unit can estimate emotions using a generative AI model that takes a child's facial expression data as input and outputs emotions. It can also estimate emotions using a generative AI model that takes a child's voice data as input and outputs emotions. Furthermore, it can estimate emotions using a generative AI model that takes a child's biometric data as input and outputs emotions. The ad filtering unit determines the priority of ads to remove based on the estimated emotions of the child. For example, if the child's emotions are unstable, the ad filtering unit can prioritize the removal of inappropriate ads. If the child's emotions are stable, the ad filtering unit can also relax the removal priority. Furthermore, if the child's emotions are heightened, the ad filtering unit can remove ads with an appropriate priority. This allows for appropriate ad filtering by determining the priority of ads to remove based on the child's emotions.

[0102] The ad filtering unit can perform filtering based on the display time of the ads. For example, the ad filtering unit can analyze the display time using AI. For instance, the ad filtering unit can analyze the display time using an AI model that takes display time data as input and outputs a filtering level. For example, the ad filtering unit can apply a stricter filtering level to ads displayed late at night. Conversely, the ad filtering unit can also relax the filtering level for ads displayed during the day. Furthermore, the ad filtering unit can apply a moderate filtering level to ads displayed in the evening. This enables appropriate ad filtering by performing filtering based on the display time.

[0103] The ad filtering unit can improve the accuracy of filtering based on the relevance of the ads. For example, the ad filtering unit can analyze the relevance of ads using AI. For instance, the ad filtering unit can analyze the relevance of ads using an AI model that takes the ad content as input and outputs relevance. For example, the ad filtering unit can relax the filtering level if the ad content is highly relevant. Conversely, the ad filtering unit can tighten the filtering level if the ad content is not relevant. Furthermore, the ad filtering unit can apply an appropriate filtering level if the ad content has a moderate level of relevance. This improves the accuracy of filtering based on the relevance of the ads, enabling appropriate ad filtering.

[0104] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0105] The filtering system may also include a learning progress monitoring unit that monitors the child's learning progress. The learning progress monitoring unit analyzes data from the child's online learning platform and evaluates their learning progress. For example, the learning progress monitoring unit can analyze learning progress using an AI model that takes data from the online learning platform as input and outputs learning progress. The learning progress monitoring unit can also acquire the child's school grade data and evaluate their learning progress. Furthermore, the learning progress monitoring unit can analyze records of the child's homework and evaluate their learning progress. As a result, by using the learning progress monitoring unit, the filtering level can be adjusted based on the child's learning progress.

[0106] The filtering system can also include a health monitoring unit to monitor the child's health status. The health monitoring unit analyzes heart rate data acquired from the child's smartwatch and evaluates their health status. For example, the health monitoring unit can analyze heart rate data using an AI model that takes smartwatch heart rate data as input and outputs health status. The health monitoring unit can also analyze sleep data acquired from the child's smart home device and evaluate their health status. Furthermore, the health monitoring unit can acquire data from the child's regular health checkups and evaluate their health status. This allows the filtering level to be adjusted based on the child's health status by using the health monitoring unit.

[0107] The filtering system can also include a behavioral analysis unit that analyzes the child's daily behavioral patterns. The behavioral analysis unit analyzes exercise data acquired from the child's smartwatch and evaluates the behavioral patterns. For example, the behavioral analysis unit can analyze the exercise data using an AI model that takes smartwatch exercise data as input and outputs behavioral patterns. The behavioral analysis unit can also analyze daily behavioral data acquired from the child's smart home devices and evaluate the behavioral patterns. Furthermore, the behavioral analysis unit can analyze the child's meal records and evaluate their nutritional status. As a result, by using the behavioral analysis unit, the filtering level can be adjusted based on the child's daily behavioral patterns.

[0108] The filtering system may also include a social media analysis unit that analyzes children's social media activity. The social media analysis unit analyzes the content of children's social media posts and reflects this in the determination of their developmental level. For example, the social media analysis unit can analyze social media posts using an AI model that takes social media posts as input and outputs a developmental level. The social media analysis unit can also analyze children's social media friendships and use this to determine their developmental level. Furthermore, the social media analysis unit can analyze the frequency of children's social media activity and reflect this in the determination of their developmental level. As a result, by using the social media analysis unit, the filtering level can be adjusted based on children's social media activity.

[0109] The filtering system may further include a location information analysis unit that analyzes the child's geographical location. The location information analysis unit analyzes the child's current location and adjusts the filtering level. For example, the location information analysis unit can analyze geographical location information using an AI model that takes geographical location information as input and outputs a filtering level. For example, the location information analysis unit can tighten the filtering level if the child's current location is at school. It can also loosen the filtering level if the child's current location is at home. Furthermore, the location information analysis unit can appropriately adjust the filtering level if the child's current location is in a public place. In this way, by using the location information analysis unit, the filtering level can be adjusted based on the child's geographical location.

[0110] The filtering system may further include an emotion adjustment unit that estimates the child's emotions and fine-tunes the filtering level based on the estimated emotions. The emotion adjustment unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the emotion adjustment unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. Alternatively, the emotion adjustment unit can estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the emotion adjustment unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The emotion adjustment unit fine-tunes the filtering level based on the estimated emotions of the child. For example, the emotion adjustment unit can tighten the filtering level if the emotions are unstable. It can also relax the filtering level if the emotions are stable. Furthermore, it can adjust the filtering level appropriately if the emotions are heightened. Thus, by using the emotion adjustment unit, the filtering level can be fine-tuned based on the child's emotions.

[0111] The filtering system may further include an emotion priority determination unit that estimates the child's emotions and determines the priority of messages to be deleted based on the estimated emotions. The emotion priority determination unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the emotion priority determination unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. Alternatively, the emotion priority determination unit can estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the emotion priority determination unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The emotion priority determination unit determines the priority of messages to be deleted based on the estimated emotions of the child. For example, if the emotions are unstable, the emotion priority determination unit can prioritize the deletion of inappropriate messages. Also, if the emotions are stable, the emotion priority determination unit can relax the deletion priority. Furthermore, if the emotions are heightened, the emotion priority determination unit can delete messages with an appropriate priority. Thus, by using the emotion priority determination unit, the priority of messages to be deleted can be determined based on the child's emotions.

[0112] The filtering system may further include an emotion content prioritization unit that estimates the child's emotions and determines the priority of content to be deleted based on the estimated emotions. The emotion content prioritization unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the emotion content prioritization unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. Alternatively, the emotion content prioritization unit can estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the emotion content prioritization unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The emotion content prioritization unit determines the priority of content to be deleted based on the estimated emotions of the child. For example, if the emotions are unstable, the emotion content prioritization unit can prioritize the deletion of inappropriate content. Also, if the emotions are stable, the emotion content prioritization unit can relax the deletion priority. Furthermore, if the emotions are heightened, the emotion content prioritization unit can delete content with an appropriate priority. Thus, by using the emotion content prioritization unit, the priority of content to be deleted can be determined based on the child's emotions.

[0113] The filtering system may further include an emotional ad prioritization unit that estimates the child's emotions and determines the priority of ads to be deleted based on the estimated emotions. The emotional ad prioritization unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the emotional ad prioritization unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. Alternatively, the emotional ad prioritization unit can estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the emotional ad prioritization unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The emotional ad prioritization unit determines the priority of ads to be deleted based on the estimated emotions of the child. For example, if the child's emotions are unstable, the emotional ad prioritization unit can prioritize the deletion of inappropriate ads. Also, if the child's emotions are stable, the emotional ad prioritization unit can relax the deletion priority. Furthermore, if the child's emotions are heightened, the emotional ad prioritization unit can delete ads with an appropriate priority. Thus, by using the emotional ad prioritization unit, the priority of ads to be deleted can be determined based on the child's emotions.

[0114] The filtering system may further include an emotion adjustment frequency determination unit that estimates the child's emotions and determines the frequency of adjusting the filtering level based on the estimated emotions. The emotion adjustment frequency determination unit estimates the child's emotions using an emotion estimation function, such as an emotion engine or a generative AI. For example, the emotion adjustment frequency determination unit can estimate emotions using a generative AI model that takes the child's facial expression data as input and outputs emotions. Alternatively, the emotion adjustment frequency determination unit can estimate emotions using a generative AI model that takes the child's voice data as input and outputs emotions. Furthermore, the emotion adjustment frequency determination unit can estimate emotions using a generative AI model that takes the child's biometric data as input and outputs emotions. The emotion adjustment frequency determination unit determines the frequency of adjusting the filtering level based on the estimated emotions of the child. For example, the emotion adjustment frequency determination unit can adjust the filtering level frequently if the emotions are unstable. Also, the emotion adjustment frequency determination unit can reduce the frequency of adjustments if the emotions are stable. Furthermore, the emotion adjustment frequency determination unit can adjust the filtering level at an appropriate frequency if the emotions are heightened. Thus, by using the emotion adjustment frequency determination unit, the frequency of adjustments to the filtering level can be determined based on the child's emotions.

[0115] The following briefly describes the processing flow for example form 2.

[0116] Step 1: The assessment unit determines the child's developmental level. The assessment unit can determine the developmental level based, for example, the child's age, usage history, and parental settings. Step 2: The adjustment unit adjusts the filtering level based on the developmental level determined by the judgment unit. The adjustment unit can dynamically adjust the filtering level using, for example, a generative AI. The adjustment unit can also periodically re-evaluate and adjust the filtering level. Step 3: The message filtering unit deletes inappropriate messages based on the filtering level adjusted by the adjustment unit. The message filtering unit can delete messages containing inappropriate words, inappropriate images, or inappropriate links, for example. Step 4: The content filtering unit removes inappropriate content based on the filtering level adjusted by the adjustment unit. The content filtering unit can remove content such as violent images, adult content, and discriminatory language. Step 5: The ad filtering unit removes inappropriate ads based on the filtering level adjusted by the adjustment unit. The ad filtering unit can remove, for example, fraudulent ads, adult ads, and ads containing violent content.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0119] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] Each of the multiple elements described above, including the determination unit, adjustment unit, message filtering unit, content filtering unit, and advertising filtering unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the determination unit is implemented by the control unit 46A of the smart device 14 and determines the developmental level based on the child's age and usage history. The adjustment unit is implemented by the specific processing unit 290 of the data processing device 12 and dynamically adjusts the filtering level using generated AI. The message filtering unit is implemented by the control unit 46A of the smart device 14 and deletes inappropriate messages. The content filtering unit is implemented by the specific processing unit 290 of the data processing device 12 and deletes inappropriate content. The advertising filtering unit is implemented by the control unit 46A of the smart device 14 and deletes inappropriate advertisements. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0121] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0122] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0124] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0125] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0128] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the determination unit, adjustment unit, message filtering unit, content filtering unit, and advertising filtering unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the determination unit is implemented by the control unit 46A of the smart glasses 214 and determines the developmental level based on the child's age and usage history. The adjustment unit is implemented by the specific processing unit 290 of the data processing device 12 and dynamically adjusts the filtering level using generated AI. The message filtering unit is implemented by the control unit 46A of the smart glasses 214 and deletes inappropriate messages. The content filtering unit is implemented by the specific processing unit 290 of the data processing device 12 and deletes inappropriate content. The advertising filtering unit is implemented by the control unit 46A of the smart glasses 214 and deletes inappropriate advertisements. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0137] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0138] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the determination unit, adjustment unit, message filtering unit, content filtering unit, and advertising filtering unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the determination unit is implemented by the control unit 46A of the headset terminal 314 and determines the developmental level based on the child's age and usage history. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and dynamically adjusts the filtering level using generated AI. The message filtering unit is implemented by the control unit 46A of the headset terminal 314 and deletes inappropriate messages. The content filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and deletes inappropriate content. The advertising filtering unit is implemented by the control unit 46A of the headset terminal 314 and deletes inappropriate advertisements. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0153] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0154] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0161] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0162] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0163] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0164] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0167] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0168] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0169] Each of the multiple elements described above, including the determination unit, adjustment unit, message filtering unit, content filtering unit, and advertising filtering unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the determination unit is implemented by the control unit 46A of the robot 414 and determines the developmental level based on the child's age and usage history. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and dynamically adjusts the filtering level using generated AI. The message filtering unit is implemented by the control unit 46A of the robot 414 and deletes inappropriate messages. The content filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and deletes inappropriate content. The advertising filtering unit is implemented by the control unit 46A of the robot 414 and deletes inappropriate advertisements. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0170] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0171] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0172] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0173] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0174] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0175] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0177] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0178] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0179] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0180] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0181] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0182] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0183] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0184] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0185] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0186] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0187] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0188] (Note 1) A unit for determining the child's developmental level, An adjustment unit that adjusts the filtering level based on the developmental level determined by the determination unit, A message filtering unit that deletes inappropriate messages based on the filtering level adjusted by the adjustment unit, A content filtering unit that deletes inappropriate content based on the filtering level adjusted by the adjustment unit, The system includes an ad filtering unit that removes inappropriate ads based on the filtering level adjusted by the adjustment unit. A system characterized by the following features. (Note 2) The determination unit, The developmental level is determined based on the child's age, usage history, and parental settings. The system described in Appendix 1, characterized by the features described herein. (Note 3) The adjustment unit is, The filtering level is dynamically adjusted based on the developmental level determined by the aforementioned determination unit. The system described in Appendix 1, characterized by the features described herein. (Note 4) The determination unit, The system estimates the child's emotions and adjusts the assessment of the child's developmental level based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The determination unit, Analyze a child's learning history and use it to determine their developmental level. The system described in Appendix 1, characterized by the features described herein. (Note 6) The determination unit, Analyze children's daily behavioral patterns and use the findings to determine their developmental level. The system described in Appendix 1, characterized by the features described herein. (Note 7) The determination unit, The system estimates the child's emotions and adjusts the display method of the assessment results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The determination unit, Monitor the child's health status and use the findings to determine their developmental level. The system described in Appendix 1, characterized by the features described herein. (Note 9) The determination unit, Analyze children's social media activity and use the results to determine their developmental level. The system described in Appendix 1, characterized by the features described herein. (Note 10) The adjustment unit is, It estimates the child's emotions and fine-tunes the filtering level based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The adjustment unit is, Dynamically adjust the filtering level according to the child's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 12) The adjustment unit is, Adjust filtering levels based on children's screen time. The system described in Appendix 1, characterized by the features described herein. (Note 13) The adjustment unit is, The system estimates the child's emotions and determines the frequency of adjustments to the filtering level based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The adjustment unit is, Adjust filtering levels based on the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 15) The adjustment unit is, Analyze your child's friendships and adjust the filtering level. The system described in Appendix 1, characterized by the features described herein. (Note 16) The message filtering unit described above, We estimate children's emotions and adjust the criteria for removing inappropriate messages based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The message filtering unit described above, The message content is analyzed and filtered according to the developmental level. The system described in Appendix 1, characterized by the features described herein. (Note 18) The message filtering unit described above, Filter messages by considering the sender's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The message filtering unit described above, The system estimates the child's emotions and determines the priority of messages to delete based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The message filtering unit described above, Filter based on the message sending time. The system described in Appendix 1, characterized by the features described herein. (Note 21) The message filtering unit described above, Improve filtering accuracy based on message relevance. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned content filtering unit, We estimate children's emotions and adjust the criteria for removing inappropriate content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned content filtering unit, Filter content according to its category. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned content filtering unit, Analyze content browsing history to improve filtering accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned content filtering unit, The system estimates the child's emotions and prioritizes content to remove based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned content filtering unit, Filtering is performed considering the attribute information of the content creator. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned content filtering unit, Improve the accuracy of filtering based on content relevance. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned advertising filtering unit is We estimate children's emotions and adjust the criteria for removing inappropriate ads based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned advertising filtering unit is Filter by ad category. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned advertising filtering unit is Analyzing ad display history improves filtering accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned advertising filtering unit is It estimates children's emotions and determines the priority of ads to remove based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned advertising filtering unit is Filter based on the ad display time. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned advertising filtering unit is Improve the accuracy of filtering based on ad relevance. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A unit for determining the child's developmental level, An adjustment unit that adjusts the filtering level based on the developmental level determined by the determination unit, A message filtering unit that deletes inappropriate messages based on the filtering level adjusted by the adjustment unit, A content filtering unit that deletes inappropriate content based on the filtering level adjusted by the adjustment unit, The system includes an ad filtering unit that removes inappropriate ads based on the filtering level adjusted by the adjustment unit. A system characterized by the following features.

2. The determination unit, The developmental level is determined based on the child's age, usage history, and parental settings. The system according to feature 1.

3. The adjustment unit is, The filtering level is dynamically adjusted based on the developmental level determined by the aforementioned determination unit. The system according to feature 1.

4. The determination unit, The system estimates the child's emotions and adjusts the assessment of the child's developmental level based on those estimated emotions. The system according to feature 1.

5. The determination unit, Analyze a child's learning history and use it to determine their developmental level. The system according to feature 1.

6. The determination unit, Analyze children's daily behavioral patterns and use the findings to determine their developmental level. The system according to feature 1.

7. The determination unit, The system estimates the child's emotions and adjusts the display method of the assessment results based on the estimated emotions. The system according to feature 1.

8. The determination unit, Monitor the child's health status and use the findings to determine their developmental level. The system according to feature 1.

Images